Software Lead - Data Science

Purpose/Objective

We are building a productiongrade analytics platform for battery assets (stationary BESS). You will lead a multidisciplinary team to correlate usage patterns with performance metrics, turning BMS/telemetry into decisions that improve reliability, safety, and margins. You will use devicelevel models together with cloud analytics to improve maintenance, optimize dispatch, and reduce warranty issues. Preference will be given to candidates with battery domain understanding.

Key Responsibilities of Role

Platform & Data Engineering - Own the end to end data architecture: ingestion from BMS/SCADA/EMS, time series storage, feature store, model serving, and secure APIs. Establish telemetry pipelines with strong data quality, lineage, observability, and SLA adherence. Analytics & Modeling (Usage & Performance Correlation) - Translate usage signals (Current/C rate, SoC, temperature/thermal profiles, cycle vs calendar aging) into performance metrics (SOH, capacity fade, impedance growth, efficiency, safety risk). Build predictive models for RUL, anomaly/failure detection, state estimation (SOC/SOH/SOx); quantify uncertainty and provide explainability. Apply Bayesian optimization and multivariate prognostics for early cycle life prediction and parameter tuning. 1. Battery User Experience Develop on device models and energy accounting for SW features; architect end to end solutions to improve perceived battery life, charging and thermal performance. Build user facing systems and interfaces that educate users/operators and guide behavior for healthier usage patterns. 1. Products, Dashboards & Decisioning Deliver operator dashboards with actionable KPIs: performance & availability, safety alerts, degradation indicators, dispatch optimization signals. Partner with EMS/controls on algorithmic hooks for energy arbitrage, peak shifting, compliance, and event analytics. 1. Reliability, MLOps & Delivery Own MLOps: experiment tracking, CI/CD for models, monitoring (drift/latency), rollback/OTA updates; drive “model in production” culture. Lead QA and site integration for new releases; validate against field data and simulation before rollout.

Technical Competencies

• Strong Python, SQL; experience with timeseries and distributed processing.,• ML/DL for time series: gradient boosting/forests, XGBoost/LightGBM; LSTM/GRU/Temporal CNN; transformers for multivariate series. ,• Statistical methods for correlation/causal analysis; experiment design (offline/online).,• Cloud architecture & MLOps (Azure/AWS, MLflow), model monitoring.

Qualifications and Experience

Bachelor’s/master’s in computer science, Data Science, Electrical/Power/Electrochemistry, or related field. 8 to 10 Yrs.